Triple
T21531281
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roman calendar |
E531234
|
entity |
| Predicate | usesReferencePoints |
P119804
|
FINISHED |
| Object | Kalends Nones Ides |
—
|
LITERAL FINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Kalends Nones Ides | Statement: [Roman calendar, usesReferencePoints, Kalends Nones Ides]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesReferencePoints Context triple: [Roman calendar, usesReferencePoints, Kalends Nones Ides]
-
A.
isReferencePointFor
Indicates that one entity serves as a positional or conceptual basis used to locate, measure, or interpret another entity.
-
B.
usesBasePoint
Indicates that one entity performs an operation or defines a structure by referencing or relying on a specific base point.
-
C.
usesCoordinateReference
Indicates that one entity adopts or relies on the coordinate reference system defined or provided by another entity.
-
D.
usesReferenceObjects
chosen
Indicates that an entity performs an action or makes a determination by relying on one or more other entities as reference points or benchmarks.
-
E.
usedReferenceFrame
Indicates that one entity adopts or relies on another entity as the coordinate system or reference frame for describing positions, motions, or measurements.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e0c45e5b8881908ac18fc2f493b114 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ee9d08ebf881909574e098404f93fa |
completed | April 26, 2026, 11:17 p.m. |
| PD | Predicate disambiguation | batch_69e6320043bc81909417c41a718652ba |
completed | April 20, 2026, 2:02 p.m. |
Created at: April 16, 2026, 6:27 p.m.